UniGrasp: Learning a Unified Model to Grasp with Multifingered Robotic Hands

Abstract

To achieve a successful grasp, gripper attributes such as its geometry and kinematics play a role as important as the object geometry. The majority of previous work has focused on developing grasp methods that generalize over novel object geometry but are specific to a certain robot hand. We propose UniGrasp, an efficient data-driven grasp synthesis method that considers both the object geometry and gripper attributes as inputs. UniGrasp is based on a novel deep neural network architecture that selects sets of contact points from the input point cloud of the object. The proposed model is trained on a large dataset to produce contact points that are in force closure and reachable by the robot hand. By using contact points as output, we can transfer between a diverse set of multifingered robotic hands. Our model produces over 90% valid contact points in Top10 predictions in simulation and more than 90% successful grasps in real world experiments for various known two-fingered and three-fingered grippers. Our model also achieves 93%, 83% and 90% successful grasps in real world experiments for an unseen two-fingered gripper and two unseen multi-fingered anthropomorphic robotic hands.

arXiv commentAccepted to IEEE Robotics and Automation Letters with ICRA 2020 option

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Data-Driven Grasp Synthesis - A Survey
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols
• Learning Representations and Generative Models for 3D Point Clouds
• PointNetGPD: Detecting Grasp Configurations from Point Sets
• TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank

Cited by in corpus (14)

• Grasp Multiple Objects with One Hand
• EfficientGrasp: A Unified Data-Efficient Learning to Grasp Method for Multi-fingered Robot Hands
• UGG: Unified Generative Grasping
• Synthesize Dexterous Nonprehensile Pregrasp for Ungraspable Objects
• Orientation Attentive Robotic Grasp Synthesis with Augmented Grasp Map Representation
• AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy
• DexRepNet++: Learning Dexterous Robotic Manipulation with Geometric and Spatial Hand-Object Representations
• DDGC: Generative Deep Dexterous Grasping in Clutter
• Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
• Tool as Embodiment for Recursive Manipulation
• Leveraging CVAE for Joint Configuration Estimation of Multifingered Grippers from Point Cloud Data
• Learning to Regrasp by Learning to Place
• 6-DoF Contrastive Grasp Proposal Network
• OmniHang: Learning to Hang Arbitrary Objects using Contact Point Correspondences and Neural Collision Estimation